Merge branch 'master' of http://git.wanmeizhensuo.com/ML/ffm-baseline

eda/esmm/Feature_pipline/get_tfrecord.py

-#!/usr/bin/env python
 #coding=utf-8
 
 from __future__ import absolute_import
@@ -26,10 +25,10 @@ tf.app.flags.DEFINE_integer("threads", 16, "threads num")
 #User_Fileds = set(['101','109_14','110_14','127_14','150_14','121','122','124','125','126','127','128','129'])
 #Ad_Fileds = set(['205','206','207','210','216'])
 #Context_Fileds = set(['508','509','702','853','301'])
-#Common_Fileds = {'1':'1','2':'2','3':'3','4':'4','5':'5','6':'6','7':'7','8':'8','9':'9','10':'10','11':'11','12':'12','13':'13','14':'14','15':'15','16':'16','17':'17','18':'18','19':'19','20':'20','21':'21','22':'22','23':'23','24':'24','25':'25','26':'26','27':'27','28':'28','29':'29','30':'30'}
-Common_Fileds = {'1':'1','2':'2','3':'3','4':'4','5':'5','6':'6','7':'7','8':'8','9':'9','10':'10','11':'11'}
-UMH_Fileds      = {'109_14':('u_cat','12'),'110_14':('u_shop','13'),'127_14':('u_brand','14'),'150_14':('u_int','15')}      #user multi-hot feature
-Ad_Fileds       = {'206':('a_cat','16'),'207':('a_shop','17'),'210':('a_int','18'),'216':('a_brand','19')}                  #ad feature for DIN
+Common_Fileds = {'1':'1','2':'2','3':'3','4':'4','5':'5','6':'6','7':'7','8':'8','9':'9','10':'10','11':'11','12':'12','13':'13','14':'14','15':'15','16':'16','17':'17','18':'18','19':'19','20':'20','21':'21','22':'22','23':'23'}
+#Common_Fileds = {'1':'1','2':'2','3':'3','4':'4','5':'5','6':'6','7':'7','8':'8','9':'9','10':'10','11':'11'}
+UMH_Fileds = {'109_14':('u_cat','12'),'110_14':('u_shop','13'),'127_14':('u_brand','14'),'150_14':('u_int','15')}      #user multi-hot feature
+Ad_Fileds = {'206':('a_cat','16'),'207':('a_shop','17'),'210':('a_int','18'),'216':('a_brand','19')}                  #ad feature for DIN
 
 #40362692,0,0,216:9342395:1.0 301:9351665:1.0 205:7702673:1.0 206:8317829:1.0 207:8967741:1.0 508:9356012:2.30259 210:9059239:1.0 210:9042796:1.0 210:9076972:1.0 210:9103884:1.0 210:9063064:1.0 127_14:3529789:2.3979 127_14:3806412:2.70805
 def gen_tfrecords(in_file):

eda/esmm/Model_pipline/DeepCvrMTL.py

-#!/usr/bin/env python
 #coding=utf-8
 
 #from __future__ import absolute_import
@@ -346,7 +345,7 @@ def main(_):
             print("-"*100)
             with open(FLAGS.data_dir + "/pred.txt", "w") as fo:
                 for prob in preds:
-                    fo.write("%f\t%f\n" % (prob['pctr'], prob['pcvr']))
+                    fo.write("%f\t%f\t%f\n" % (prob['pctr'], prob['pcvr'], prob['pctcvr']))
     elif FLAGS.task_type == 'export':
         print("Not Implemented, Do It Yourself!")
         #feature_spec = tf.feature_column.make_parse_example_spec(feature_columns)

eda/esmm/Model_pipline/send_mail.py

-# -*- coding: utf-8 -*-
+#coding=utf-8
 
 import smtplib
 from email.mime.text import MIMEText

eda/esmm/Model_pipline/sort_and_2sql.py

+#coding=utf-8
+
 from sqlalchemy import create_engine
 import pandas as pd
 import pymysql
@@ -17,39 +19,30 @@ def con_sql(sql):
     return result
 
 def set_join(lst):
-    return ','.join(set(lst))
+    return ','.join([str(i) for i in set(lst)])
 
 def main():
-    sql = "select device_id,city_id,cid from esmm_data2ffm_infer_native"
-    result = con_sql(sql)
-    dct = {"uid":[],"city":[],"cid_id":[]}
-    for i in result:
-        dct["uid"].append(i[0])
-        dct["city"].append(i[1])
-        dct["cid_id"].append(i[2])
-
-    df1 = pd.read_csv("/home/gaoyazhe/data/native/pred.txt",sep='\t',header=None,names=["ctr","cvr"])
-    df2 = pd.DataFrame(dct)
-    df2["ctr"],df2["cvr"] = df1["ctr"],df1["cvr"]
-    df3 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="cvr",ascending=False)).reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':set_join}).reset_index(drop=False)
+
+    # native queue
+    df2 = pd.read_csv('/home/gaoyazhe/data/native.csv',usecols=[0,1,2],header=0,names=['uid','city','cid_id'],sep='\t')
+    df2['cid_id'] = df2['cid_id'].astype('object')
+
+    df1 = pd.read_csv("/home/gaoyazhe/data/native/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
+    df2["ctr"],df2["cvr"],df2["ctcvr"] = df1["ctr"],df1["cvr"],df1["ctcvr"]
+    df3 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="ctcvr",ascending=False)).reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':set_join}).reset_index(drop=False)
     ctime = int(time.time())
     df3["time"] = ctime
     df3.columns = ["device_id","city_id","native_queue","time"]
     print("native_device_count",df3.shape)
 
 
-    sql_nearby = "select device_id,city_id,cid from esmm_data2ffm_infer_nearby"
-    result = con_sql(sql_nearby)
-    dct = {"uid":[],"city":[],"cid_id":[]}
-    for i in result:
-        dct["uid"].append(i[0])
-        dct["city"].append(i[1])
-        dct["cid_id"].append(i[2])
+    # nearby queue
+    df2 = pd.read_csv('/home/gaoyazhe/data/nearby.csv',usecols=[0,1,2],header=0,names=['uid','city','cid_id'],sep='\t')
+    df2['cid_id'] = df2['cid_id'].astype('object')
 
-    df1 = pd.read_csv("/home/gaoyazhe/data/nearby/pred.txt",sep='\t',header=None,names=["ctr","cvr"])
-    df2 = pd.DataFrame(dct)
-    df2["ctr"],df2["cvr"] = df1["ctr"],df1["cvr"]
-    df4 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="cvr",ascending=False)).reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':set_join}).reset_index(drop=False)
+    df1 = pd.read_csv("/home/gaoyazhe/data/nearby/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
+    df2["ctr"], df2["cvr"], df2["ctcvr"] = df1["ctr"], df1["cvr"], df1["ctcvr"]
+    df4 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="ctcvr",ascending=False)).reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':set_join}).reset_index(drop=False)
     df4.columns = ["device_id","city_id","nearby_queue"]
     print("nearby_device_count",df4.shape)
 

eda/esmm/Model_pipline/submit.sh

@@ -3,11 +3,11 @@ PYTHON_PATH=/home/gaoyazhe/miniconda3/bin/python
 MODEL_PATH=/srv/apps/ffm-baseline/eda/esmm
 DATA_PATH=/home/gaoyazhe/data
 
-echo "start timestamp"
+echo "start time"
 current=$(date "+%Y-%m-%d %H:%M:%S")
 timeStamp=$(date -d "$current" +%s)
 currentTimeStamp=$((timeStamp*1000+`date "+%N"`/1000000))
-echo $currentTimeStamp
+echo $current
 
 echo "rm leave tfrecord"
 rm ${DATA_PATH}/tr/*
@@ -15,11 +15,8 @@ rm ${DATA_PATH}/va/*
 rm ${DATA_PATH}/native/*
 rm ${DATA_PATH}/nearby/*
 
-echo "mysql to csv"
-mysql -u root -p3SYz54LS9#^9sBvC -h 10.66.157.22 -P 4000 -D jerry_test -e "select number,data from esmm_data2ffm_train" > ${DATA_PATH}/tr.csv
-mysql -u root -p3SYz54LS9#^9sBvC -h 10.66.157.22 -P 4000 -D jerry_test -e "select number,data from esmm_data2ffm_cv" > ${DATA_PATH}/va.csv
-mysql -u root -p3SYz54LS9#^9sBvC -h 10.66.157.22 -P 4000 -D jerry_test -e "select number,data from esmm_data2ffm_infer_native" > ${DATA_PATH}/native.csv
-mysql -u root -p3SYz54LS9#^9sBvC -h 10.66.157.22 -P 4000 -D jerry_test -e "select number,data from esmm_data2ffm_infer_nearby" > ${DATA_PATH}/nearby.csv
+echo "data2ffm"
+${PYTHON_PATH} ${MODEL_PATH}/Feature_pipline/data2ffm.py > ${DATA_PATH}/infer.log
 
 echo "split data"
 split -l $((`wc -l < ${DATA_PATH}/tr.csv`/15)) ${DATA_PATH}/tr.csv -d -a 4 ${DATA_PATH}/tr/tr_ --additional-suffix=.csv
@@ -43,35 +40,35 @@ rm ${DATA_PATH}/va/va_*
 rm ${DATA_PATH}/native/native_*
 rm ${DATA_PATH}/nearby/nearby_*
 
-echo "data transform timestamp"
+echo "data transform time"
 current=$(date "+%Y-%m-%d %H:%M:%S")
 timeStamp=$(date -d "$current" +%s)
 currentTimeStamp=$((timeStamp*1000+`date "+%N"`/1000000))
-echo $currentTimeStamp
+echo $current
 
 echo "train..."
-${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/DeepCvrMTL.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=354332 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir="${DATA_PATH}" --task_type="train"
+${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/DeepCvrMTL.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=23 --feature_size=354332 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
 
-echo "train timestamp"
+echo "train time"
 current=$(date "+%Y-%m-%d %H:%M:%S")
 timeStamp=$(date -d "$current" +%s)
 currentTimeStamp=$((timeStamp*1000+`date "+%N"`/1000000))
-echo $currentTimeStamp
-
-${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/send_mail.py
+echo $current
 
 echo "infer native..."
-${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/DeepCvrMTL.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=354332 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir="${DATA_PATH}/native" --task_type="infer" > ${DATA_PATH}/infer.log
+${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/DeepCvrMTL.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=354332 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/infer.log
 
 
 echo "infer nearby..."
-${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/DeepCvrMTL.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=354332 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir="${DATA_PATH}/nearby" --task_type="infer" > ${DATA_PATH}/infer.log
+${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/DeepCvrMTL.py --ctr_task_wgt=0.3 --learning_rate=0.0001 --deep_layers=256,128 --dropout=0.8,0.5 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=354332 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/infer.log
 
 echo "sort and 2sql"
 ${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/sort_and_2sql.py
 
-echo "infer and sort and 2sql timestamp"
+echo "infer and sort and 2sql time"
 current=$(date "+%Y-%m-%d %H:%M:%S")
 timeStamp=$(date -d "$current" +%s)
 currentTimeStamp=$((timeStamp*1000+`date "+%N"`/1000000))
-echo $currentTimeStamp
\ No newline at end of file
+echo $current
+
+${PYTHON_PATH} ${MODEL_PATH}/Model_pipline/send_mail.py
\ No newline at end of file

eda/feededa/src/main/scala/com/gmei/EsmmData.scala

@@ -283,7 +283,7 @@ object EsmmPredData {
         case (device_city, cid_data) =>
           val device_id = Try(device_city.split(",")(0)).getOrElse("")
           val city_id = Try(device_city.split(",")(1)).getOrElse("")
-          val cids = Try(cid_data.toSeq.map(_.getAs[String]("merge_queue").split(",")).flatMap(_.zipWithIndex).sortBy(_._2).map(_._1).distinct.take(300).mkString(",")).getOrElse("")
+          val cids = Try(cid_data.toSeq.map(_.getAs[String]("merge_queue").split(",")).flatMap(_.zipWithIndex).sortBy(_._2).map(_._1).distinct.take(500).mkString(",")).getOrElse("")
           (device_id,city_id ,s"$cids")
       }.filter(_._3!="").toDF("device_id","city_id","merge_queue")
       raw_data1.createOrReplaceTempView("raw_data1")
@@ -312,7 +312,7 @@ object EsmmPredData {
       val native_data1 = sc.sql(
         s"""
            |select device_id,city_id as ucity_id,
-           |explode(split(split(native_queue, concat(',',split(native_queue,',')[300]))[0],',')) as cid_id
+           |explode(split(split(native_queue, concat(',',split(native_queue,',')[500]))[0],',')) as cid_id
            |from native_data
          """.stripMargin
       ).withColumn("label",lit(0))

eda/merge_sort.py

+def merge_sort(lst):
+    if len(lst) <= 1:
+        return lst
+    middle = int(len(lst) / 2)
+    left = merge_sort(lst[:middle])
+    right = merge_sort(lst[middle:])
+    merged = []
+    while left and right:
+        merged.append(left.pop(0) if left[0] <= right[0] else right.pop(0))
+    merged.extend(right if right else left)
+    return merged
+data_lst = [6,202,100,301,38,8,1]
+print(merge_sort(data_lst))
\ No newline at end of file

tensnsorflow/ffm.py

@@ -140,16 +140,23 @@ def get_data():
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select max(stat_date) from esmm_train_data"
     validate_date = con_sql(db, sql)[0].values.tolist()[0]
-    print("validate_date:"+validate_date)
+    print("validate_date:" + validate_date)
     temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    start = (temp - datetime.timedelta(days=14)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=15)).strftime("%Y-%m-%d")
+    print(start)
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select device_id,y,z,stat_date,ucity_id,cid_id,clevel1_id,ccity_name from esmm_train_data " \
-          "where stat_date >= '{}'".format(start)
-    df = con_sql(db,sql)
-    df = df.rename(columns={0:"device_id",1: "y",2:"z",3:"stat_date",4:"ucity_id",5:"cid_id",
-                                6:"clevel1_id",7:"ccity_name"})
+    sql = "select e.device_id,e.y,e.z,e.stat_date,e.ucity_id,e.cid_id,e.clevel1_id,e.ccity_name," \
+          "u.device_type,u.manufacturer,u.channel," \
+          "home.jingxuan,home.zhibo,home.nose,home.eyes,home.weizheng,home.teeth,home.lunkuo," \
+          "home.meifu,home.xizhi,home.zhifang,home.longxiong,home.simi,home.maofa,home.gongli,home.korea " \
+          "from esmm_train_data e left join user_feature u on e.device_id = u.device_id " \
+          "left join home_tab_click home on e.device_id = home.device_id " \
+          "where e.stat_date >= '{}'".format(start)
+    df = con_sql(db, sql)
+    df = df.rename(columns={0: "device_id", 1: "y", 2: "z", 3: "stat_date", 4: "ucity_id", 5: "cid_id",
+                            6: "clevel1_id", 7: "ccity_name"})
     print("esmm data ok")
+    print(df.head(2))
     ucity_id = list(set(df["ucity_id"].values.tolist()))
     cid = list(set(df["cid_id"].values.tolist()))
     df["clevel1_id"] = df["clevel1_id"].astype("str")
@@ -158,16 +165,16 @@ def get_data():
     df["z"] = df["z"].astype("str")
     df["y"] = df["stat_date"].str.cat([df["device_id"].values.tolist(),df["ucity_id"].values.tolist(), df["cid_id"].values.tolist(),
                                        df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
-    df = df.drop("z", axis=1)
-    df = pd.merge(df,get_statistics(),how='left',on = "device_id").fillna(0)
-    df = df.drop("device_id", axis=1)
+    df = df.drop(["z","device_id"], axis=1).fillna(0.0)
     print(df.head(2))
+    print("fields:{}".format(df.shape[1]-1))
+    print("features:{}".format(len(cid)))
     return df,validate_date,ucity_id,cid
 
 
 def transform(a,validate_date):
     model = multiFFMFormatPandas()
-    df = model.fit_transform(a, y="y", n=160000, processes=22)
+    df = model.fit_transform(a, y="y", n=160000, processes=26)
     df = pd.DataFrame(df)
     df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
     df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
@@ -187,51 +194,30 @@ def transform(a,validate_date):
     test = test.drop("stat_date",axis=1)
     # print("train shape")
     # print(train.shape)
-    train.to_csv(path + "train.csv", sep="\t", index=False)
-    test.to_csv(path + "test.csv", sep="\t", index=False)
+    # train.to_csv(path + "train.csv", sep="\t", index=False)
+    # test.to_csv(path + "test.csv", sep="\t", index=False)
 
     return model
 
-def get_user_feature():
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select max(stat_date) from esmm_train_data"
-    validate_date = con_sql(db, sql)[0].values.tolist()[0]
-    print("validate_date:" + validate_date)
-    temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    start = (temp - datetime.timedelta(days=2)).strftime("%Y-%m-%d")
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select e.device_id,e.y,e.z,e.stat_date,e.ucity_id,e.cid_id,e.clevel1_id,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,home.total" \
-          "from (esmm_train_data e left join user_feature u on e.device_id = u.device_id) " \
-          "left join home_tab_click home on e.device_id = home.device_id" \
-          "where e.stat_date >= '{}'".format(start)
-    df = con_sql(db, sql)
-    df = df.rename(columns={0: "device_id", 1: "y", 2: "z", 3: "stat_date", 4: "ucity_id", 5: "cid_id",
-                            6: "clevel1_id", 7: "ccity_name"})
-    print(df.head(2))
-
-def get_statistics():
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select device_id,total,精选,直播,鼻部,眼部,微整,牙齿,轮廓,美肤抗衰," \
-          "吸脂,脂肪填充,隆胸,私密,毛发管理,公立,韩国 from home_tab_click"
-    df = con_sql(db, sql)
-    df = df.rename(columns={0:"device_id",1:"total"})
-    for i in df.columns.difference(["device_id","total"]):
-        df[i] = df[i]/df["total"]
-        df[i] = df[i].apply(lambda x: format(x,".4f"))
-        df[i] = df[i].astype("float")
-    df = df.drop("total", axis=1)
-    return df
-
 
 def get_predict_set(ucity_id, cid,model):
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select device_id,y,z,stat_date,ucity_id,cid_id,clevel1_id,ccity_name,label from esmm_pre_data"
+    sql = "select e.device_id,e.y,e.z,e.stat_date,e.ucity_id,e.cid_id,e.clevel1_id,e.ccity_name," \
+          "u.device_type,u.manufacturer,u.channel," \
+          "home.jingxuan,home.zhibo,home.nose,home.eyes,home.weizheng,home.teeth,home.lunkuo," \
+          "home.meifu,home.xizhi,home.zhifang,home.longxiong,home.simi,home.maofa,home.gongli,home.korea,e.label " \
+          "from esmm_pre_data e left join user_feature u on e.device_id = u.device_id " \
+          "left join home_tab_click home on e.device_id = home.device_id"
     df = con_sql(db, sql)
     df = df.rename(columns={0: "device_id", 1: "y", 2: "z", 3: "stat_date", 4: "ucity_id", 5: "cid_id",
-                            6: "clevel1_id", 7: "ccity_name",8:"label"})
+                            6: "clevel1_id", 7: "ccity_name",26:"label"})
+    print("before filter:")
+    print(df.shape)
     df = df[df["cid_id"].isin(cid)]
+    print("after cid filter:")
+    print(df.shape)
     df = df[df["ucity_id"].isin(ucity_id)]
+    print("after ucity filter:")
     print(df.shape)
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["cid_id"] = df["cid_id"].astype("str")
@@ -241,11 +227,7 @@ def get_predict_set(ucity_id, cid,model):
     df["y"] = df["label"].str.cat(
         [df["device_id"].values.tolist(), df["ucity_id"].values.tolist(), df["cid_id"].values.tolist(),
          df["y"].values.tolist(), df["z"].values.tolist()], sep=",")
-    df = df.drop(["z","label"], axis=1)
-    df = pd.merge(df, get_statistics(), how='left',on = "device_id").fillna(0)
-    df = df.drop("device_id", axis=1)
-    print("df ok")
-    print(df.shape)
+    df = df.drop(["z","label","device_id"], axis=1).fillna(0.0)
     print(df.head(2))
     df = model.transform(df,n=160000, processes=22)
     df = pd.DataFrame(df)
@@ -276,15 +258,13 @@ def get_predict_set(ucity_id, cid,model):
 
 
 if __name__ == "__main__":
-    get_user_feature()
-
     path = "/home/gmuser/ffm/"
     a = time.time()
-    # df, validate_date, ucity_id, cid = get_data()
-    # model = transform(df, validate_date)
-    # get_predict_set(ucity_id, cid,model)
-    # b = time.time()
-    # print("cost(分钟)")
-    # print((b-a)/60)
+    df, validate_date, ucity_id, cid = get_data()
+    model = transform(df, validate_date)
+    get_predict_set(ucity_id, cid,model)
+    b = time.time()
+    print("cost(分钟)")
+    print((b-a)/60)